SobeyMIL/MVOC
code for "MVOC:atraining-free multiple video object composition method with diffusion models"
This project helps video editors and content creators combine multiple moving objects from different videos into a single, cohesive video. You provide separate video clips of subjects (like a boat and a surfer) and it outputs a new video where they are blended naturally, maintaining their original movement and appearance. It's for anyone needing to create complex scenes from existing footage without extensive manual editing.
No commits in the last 6 months.
Use this if you need to realistically composite several video subjects into a new scene while preserving their individual motions and identities.
Not ideal if you're looking for a simple drag-and-drop video editing tool or need to generate entirely new video content from text prompts.
Stars
23
Forks
2
Language
Python
License
MIT
Category
Last pushed
Jul 03, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/SobeyMIL/MVOC"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
hao-ai-lab/FastVideo
A unified inference and post-training framework for accelerated video generation.
ModelTC/LightX2V
Light Image Video Generation Inference Framework
thu-ml/TurboDiffusion
TurboDiffusion: 100–200× Acceleration for Video Diffusion Models
PKU-YuanGroup/Helios
Helios: Real Real-Time Long Video Generation Model
PKU-YuanGroup/MagicTime
[TPAMI 2025🔥] MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators